Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal. Use when the user says "correct course" or "propose sprint change"
.claude/skills/bmad-code-org-bmad-correct-course/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 252% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 229% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 186% | 0% |
Goal: Manage significant changes during sprint execution by analyzing impact across all project artifacts and producing a structured Sprint Change Proposal.
Your Role: You are a Developer navigating change management. Analyze the triggering issue, assess impact across PRD, epics, architecture, and UX artifacts, and produce an actionable Sprint Change Proposal with clear handoff.
checklist.md) resolve from the skill root.{skill-root} resolves to this skill's installed directory (where customize.toml lives).{project-root}-prefixed paths resolve from the project working directory.{skill-name} resolves to the skill directory's basename.Run: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow
If the script is not found, BMad is not set up here. Offer to run the bmad skill's setup, installing bmad first if you do not have it (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run the command again.
If it fails for any other reason, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
{skill-root}/customize.toml — defaults{project-root}/_bmad/custom/{skill-name}.toml — team overrides{project-root}/_bmad/custom/{skill-name}.user.toml — personal overridesAny missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.
Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.
Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} — load the referenced contents as facts. All other entries are facts verbatim.
Run: uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key core.project_name --key modules.bmm.implementation_artifacts --key modules.bmm.planning_artifacts --key modules.bmm.project_knowledge
date as system-generated current datetimeGreet the user.
Execute each entry in {workflow.activation_steps_append} in order.
Activation is complete. If activation_steps_prepend or activation_steps_append were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.
default_output_file = {planning_artifacts}/sprint-change-proposal-{date}.md| Input | Path | Load Strategy | |-------|------|---------------| | PRD | {planning_artifacts}/*prd*.md (whole) or {planning_artifacts}/*prd*/*.md (sharded) | FULL_LOAD | | Epics | {planning_artifacts}/*epic*.md (whole) or {planning_artifacts}/*epic*/*.md (sharded) | FULL_LOAD | | Architecture | {planning_artifacts}/*architecture*.md (whole) or {planning_artifacts}/*architecture*/*.md (sharded) | FULL_LOAD | | UX Design | {planning_artifacts}/*ux*.md (whole) or {planning_artifacts}/*ux*/*.md (sharded) | FULL_LOAD | | Spec | {planning_artifacts}/*spec-*.md (whole) | FULL_LOAD | | Project Context | AGENTS.md in the affected repo (the bmad:context block) | FULL_LOAD |
Strategy: Course correction needs broad project context to assess change impact accurately. Load all available planning artifacts.
Discovery Process for FULL_LOAD documents (PRD, Epics, Architecture, UX Design, Spec):
*prd*.md, *epic*.md, *architecture*.md, *ux*.md, *spec-*.md)index.md (e.g., prd/index.md, epics/index.md)index.md to understand the document structureDiscovery Process for Project Context:
AGENTS.md in the repo the change affects — the block between the bmad:context markers carries the policy, frozen paths, and conventions a course correction must respect.AGENTS.md (greenfield projects).Fuzzy matching: Be flexible with document names — users may use variations like prd.md, bmm-prd.md, product-requirements.md, etc.
Missing documents: Not all documents may exist. PRD and Epics are essential; Architecture, UX Design, Spec, and Document Project are loaded if available. HALT if PRD or Epics cannot be found.
<workflow>
<step n="1" goal="Initialize Change Navigation"> <action>Confirm change trigger and gather user description of the issue</action> <action>Ask: "What specific issue or change has been identified that requires navigation?"</action> <action>Verify access to project documents:</action>
<action>Ask user for mode preference:</action>
<action>Store mode selection for use throughout workflow</action>
<action if="change trigger is unclear">HALT: "Cannot navigate change without clear understanding of the triggering issue. Please provide specific details about what needs to change and why."</action>
<action if="PRD or Epics are unavailable">HALT: "Need access to PRD and Epics to assess change impact. Please ensure these documents are accessible. Architecture and UI/UX will be used if available."</action> </step>
<step n="2" goal="Execute Change Analysis Checklist"> <action>Read fully and follow the systematic analysis from: checklist.md</action> <action>Work through each checklist section interactively with the user</action> <action>Record status for each checklist item:</action>
<action>Maintain running notes of findings and impacts discovered</action> <action>Present checklist progress after each major section</action>
<action if="checklist cannot be completed">Identify blocking issues and work with user to resolve before continuing</action> </step>
<step n="3" goal="Draft Specific Change Proposals"> <action>Based on checklist findings, create explicit edit proposals for each identified artifact</action>
<action>For Story changes:</action>
Story: STORY-123] User Authentication Section: Acceptance Criteria
OLD:
NEW:
Rationale: Security requirement identified during implementation
<action>For PRD modifications:</action>
<action>For Architecture changes:</action>
<action>For UI/UX specification updates:</action>
<check if="mode is Incremental"> <action>Present each edit proposal individually</action> <action>HALT and give the user a choice:
</action> <action>If the user chooses Approve, keep the proposal. If they choose Edit, refine it with them. If they choose Skip, drop it. Continue to the next proposal.</action> </check>
<action if="mode is Batch">Collect all edit proposals and present together at end of step</action>
</step>
<step n="4" goal="Generate Sprint Change Proposal"> <action>Compile comprehensive Sprint Change Proposal document with following sections:</action>
<action>Section 1: Issue Summary</action>
<action>Section 2: Impact Analysis</action>
<action>Section 3: Recommended Approach</action>
<action>Section 4: Detailed Change Proposals</action>
<action>Section 5: Implementation Handoff</action>
<action>Present complete Sprint Change Proposal to user</action> <action>Write Sprint Change Proposal document to {default_output_file}</action> <action>HALT and give the user a choice:
</action> <action>If the user chooses Edit, revise the proposal with them and write the updated document before continuing.</action> </step>
<step n="5" goal="Finalize and Route for Implementation"> <action>Get explicit user approval for complete proposal</action> <ask>Do you approve this Sprint Change Proposal for implementation? (yes/no/revise)</ask>
<check if="no or revise"> <action>Gather specific feedback on what needs adjustment</action> <action>Return to appropriate step to address concerns</action> <goto step="3">If changes needed to edit proposals</goto> <goto step="4">If changes needed to overall proposal structure</goto>
</check>
<check if="yes the proposal is approved by the user"> <action>Finalize Sprint Change Proposal document</action> <action>Determine change scope classification:</action>
<action>Provide appropriate handoff based on scope:</action>
</check>
<check if="Minor scope"> <action>Route to: Developer agent for direct implementation</action> <action>Deliverables: Finalized edit proposals and implementation tasks</action> </check>
<check if="Moderate scope"> <action>Route to: Product Owner / Developer agents</action> <action>Deliverables: Sprint Change Proposal + backlog reorganization plan</action> </check>
<check if="Major scope"> <action>Route to: Product Manager / Solution Architect</action> <action>Deliverables: Complete Sprint Change Proposal + escalation notice</action>
<action>Confirm handoff completion and next steps with user</action> <action>Document handoff in workflow execution log</action> </check>
</step>
<step n="6" goal="Workflow Completion"> <action>Summarize workflow execution:</action>
<action>Confirm all deliverables produced:</action>
<action>Report workflow completion to user: "Correct Course workflow complete!"</action> <action>Remind user of success criteria and next steps for Developer agent</action> <action>Run: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow.on_complete — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action> </step>
</workflow>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 40,924 | 8,262 | -80% | 1 | 1 | 0% | 6,659 | 3,687 | -45% | 0 | 0 | — |
case-02 | fail→fail | 58,610 | 9,105 | -84% | 1 | 1 | 0% | 8,262 | 3,695 | -55% | 0 | 0 | — |
case-03 | fail→pass | 11,289 | 24,227 | +115% | 1 | 1 | 0% | 1,342 | 4,724 | +252% | 0 | 0 | — |
case-04 | pass→fail | 40,129 | 18,628 | -54% | 1 | 1 | 0% | 3,816 | 5,323 | +39% | 0 | 0 | — |
case-05 | pass→fail | 24,779 | 15,739 | -36% | 1 | 1 | 0% | 4,222 | 6,031 | +43% | 0 | 0 | — |
case-06 | pass→fail | 26,051 | 13,038 | -50% | 1 | 1 | 0% | 4,272 | 5,499 | +29% | 0 | 0 | — |
case-07 | fail→pass | 16,121 | 14,856 | -8% | 1 | 1 | 0% | 2,262 | 5,530 | +144% | 0 | 0 | — |
case-08 | pass→pass | 27,417 | 9,535 | -65% | 1 | 1 | 0% | 2,395 | 4,603 | +92% | 0 | 0 | — |
case-09 | fail→pass | 10,394 | 24,114 | +132% | 1 | 1 | 0% | 1,329 | 4,366 | +229% | 0 | 0 | — |
case-10 | fail→pass | 15,483 | 7,277 | -53% | 1 | 1 | 0% | 2,413 | 4,657 | +93% | 0 | 0 | — |
case-11 | pass→pass | 11,832 | 4,089 | -65% | 1 | 1 | 0% | 979 | 3,958 | +304% | 0 | 0 | — |
case-12 | fail→pass | 9,161 | 3,913 | -57% | 1 | 1 | 0% | 1,344 | 3,842 | +186% | 0 | 0 | — |
case-13 | fail→pass | 14,264 | 4,675 | -67% | 1 | 1 | 0% | 2,042 | 4,138 | +103% | 0 | 0 | — |
case-14 | pass→pass | 10,635 | 8,036 | -24% | 1 | 1 | 0% | 1,689 | 4,657 | +176% | 0 | 0 | — |
case-15 | pass→pass | 5,085 | 3,273 | -36% | 1 | 1 | 0% | 659 | 3,633 | +451% | 0 | 0 | — |
case-16 | pass→pass | 11,925 | 4,289 | -64% | 1 | 1 | 0% | 1,729 | 3,802 | +120% | 0 | 0 | — |
case-17 | pass→pass | 10,383 | 9,271 | -11% | 1 | 1 | 0% | 1,711 | 4,634 | +171% | 0 | 0 | — |
case-18 | fail→pass | 13,499 | 3,732 | -72% | 1 | 1 | 0% | 1,802 | 3,868 | +115% | 0 | 0 | — |
case-19 | fail→fail | 27,552 | 2,865 | -90% | 1 | 1 | 0% | 2,324 | 3,688 | +59% | 0 | 0 | — |
case-20 | fail→pass | 8,659 | 2,909 | -66% | 1 | 1 | 0% | 1,216 | 3,644 | +200% | 0 | 0 | — |
case-21 | pass→pass | 6,344 | 4,880 | -23% | 1 | 1 | 0% | 984 | 3,846 | +291% | 0 | 0 | — |
case-22 | fail→pass | 14,417 | 2,971 | -79% | 1 | 1 | 0% | 1,011 | 3,572 | +253% | 0 | 0 | — |
case-23 | fail→pass | 13,049 | 2,846 | -78% | 1 | 1 | 0% | 2,084 | 3,676 | +76% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +30 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.